183 ms median and 430 ms P95 time to first audio on Coval (30 days to October 27, 2026): Visible delay speed tier.
Benchmark summary: Visible delay speed tier on Coval's P95 (the voice becomes a visible part of the delay), a tie within 10 ms with Rime Coda on slow turns.
Deepdub PhantomZ 4.0 is a proprietary text-to-speech (TTS) API from Deepdub, measured by one independent benchmark, Coval.
Speed tier
Visible delayP95 over 293 ms. The voice becomes a visible part of the delay.
Figures as of October 27, 2026. No combined score: methodology
Gradium TTS vs Deepdub PhantomZ 4.0 Fastest TTS APIs, by speed tierOn Coval's 30-day window ending October 27, 2026 (2,796 runs from US East), Deepdub PhantomZ 4.0 starts speaking after 183.4 ms on a typical turn (median) and 430 ms on a slow turn (P95, the slowest one in twenty). That P95 is 21st lowest of the 31 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay. On the median it is a tie (gap under 10 ms) with ElevenLabs Eleven v4 Turbo and ElevenLabs Flash v2.5.
Speko, Artificial Analysis and Cekura do not rate its voice quality.
Speko, Artificial Analysis and Cekura have not tested how it reads hard text.
No list price is published by Coval, Speko, Artificial Analysis or Cekura for this model.
Rime Coda is a proprietary text-to-speech (TTS) API from Rime, measured by four independent benchmarks: Artificial Analysis, Cekura, Coval and Speko.
Out of Set Airy TTS is a proprietary text-to-speech (TTS) API from Out of Set, measured by two independent benchmarks: Coval and Speko.
Cartesia Sonic 3.5 is a proprietary text-to-speech (TTS) API from Cartesia, measured by four independent benchmarks: Artificial Analysis, Cekura, Coval and Speko.